Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0217. Min Range: -5.0217
Max Act: 5.0217. Min Act: -0.1700
Data Index: 7107121 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.8967. Min Act: -0.1700
Data Index: 388521 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.7092. Min Act: -0.1700
Data Index: 738335 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.7405. Min Act: -0.1700
Data Index: 1185559 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.6155. Min Act: -0.1700
Data Index: 3451651 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5530. Min Act: -0.1700
Data Index: 4228417 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5530. Min Act: -0.1700
Data Index: 5670195 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5460879 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5217. Min Act: -0.1700
Data Index: 6075438 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4905. Min Act: -0.1700
Data Index: 1110487 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5217. Min Act: -0.1700
Data Index: 7021606 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5530. Min Act: -0.1700
Data Index: 131289 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.5530. Min Act: -0.1700
Data Index: 2840726 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4905. Min Act: -0.1700
Data Index: 5864468 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4905. Min Act: -0.1700
Data Index: 5684228 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4905. Min Act: -0.1700
Data Index: 1369585 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4905. Min Act: -0.1700
Data Index: 2434403 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4592. Min Act: -0.1700
Data Index: 7126284 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4280. Min Act: -0.1700
Data Index: 8328262 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0217. Min Range: -5.0217
Max Act: 4.4592. Min Act: -0.1700
Data Index: 4530056 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19